{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:76QB5FAYVB7HLHHOKYPSM7QY3G","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"84526f6b4838fd3a63e3d0ba0e0d056121e8c5074caff5b2d88e2fc578712e89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-17T20:16:46Z","title_canon_sha256":"2c6a1945d35e792167ab35201fcc2b6e1c7f022657afa5b76332eb16cf5ef0a2"},"schema_version":"1.0","source":{"id":"2105.08140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.08140","created_at":"2026-07-05T02:40:52Z"},{"alias_kind":"arxiv_version","alias_value":"2105.08140v1","created_at":"2026-07-05T02:40:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08140","created_at":"2026-07-05T02:40:52Z"},{"alias_kind":"pith_short_12","alias_value":"76QB5FAYVB7H","created_at":"2026-07-05T02:40:52Z"},{"alias_kind":"pith_short_16","alias_value":"76QB5FAYVB7HLHHO","created_at":"2026-07-05T02:40:52Z"},{"alias_kind":"pith_short_8","alias_value":"76QB5FAY","created_at":"2026-07-05T02:40:52Z"}],"graph_snapshots":[{"event_id":"sha256:146210dc602e6f7e7babe2087f43c1ba249236e8a8da9683078b1c8ab85ede58","target":"graph","created_at":"2026-07-05T02:40:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2105.08140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration. However, existing Q-learning and actor-critic based off-policy RL algorithms fail when bootstrapping from out-of-distribution (OOD) actions or states. We hypothesize that a key missing ingredient from the existing methods is a proper treatment of uncertainty in the offline setting. We propose Uncertainty Weighted Actor-Critic (UWAC), an algorithm that detects OOD state-action pairs and down-weights their contribution in the training objectives accordi","authors_text":"Hanlin Goh, Jian Zhang, Joshua Susskind, Nitish Srivastava, Ruslan Salakhutdinov, Shuangfei Zhai, Yue Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-17T20:16:46Z","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08140","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7790095203639c1b93d834536373671f468b9b97b826cf14f37ec287cca00363","target":"record","created_at":"2026-07-05T02:40:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"84526f6b4838fd3a63e3d0ba0e0d056121e8c5074caff5b2d88e2fc578712e89","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-17T20:16:46Z","title_canon_sha256":"2c6a1945d35e792167ab35201fcc2b6e1c7f022657afa5b76332eb16cf5ef0a2"},"schema_version":"1.0","source":{"id":"2105.08140","kind":"arxiv","version":1}},"canonical_sha256":"ffa01e9418a87e759cee561f267e18d99366d2d8f22fd9a0a85529b1b76f4899","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffa01e9418a87e759cee561f267e18d99366d2d8f22fd9a0a85529b1b76f4899","first_computed_at":"2026-07-05T02:40:52.041701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:52.041701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nyO9OKC0Jw73C9eFiZk7r6YAwzcBikwzdL7P+sKDS1RbfbthSUqzrzSd2eMSVDY7aw5tjv9R4ba9MOwO5VReAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:52.042258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.08140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7790095203639c1b93d834536373671f468b9b97b826cf14f37ec287cca00363","sha256:146210dc602e6f7e7babe2087f43c1ba249236e8a8da9683078b1c8ab85ede58"],"state_sha256":"5dc79b80d5ed12ca674467063c678929a3492d5884ab98e09178c22dd89e6e6d"}